Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2439 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0877. Min Range: -5.0877
Max Act: 5.0877. Min Act: -0.1700
Data Index: 2737778 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0877. Min Range: -5.0877
Max Act: 5.0564. Min Act: -0.1700
Data Index: 6040133 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0877. Min Range: -5.0877
Max Act: 5.0564. Min Act: -0.1700
Data Index: 4569740 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0877. Min Range: -5.0877
Max Act: 5.0252. Min Act: -0.1700
Data Index: 3959986 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0877. Min Range: -5.0877
Max Act: 5.0252. Min Act: -0.1700
Data Index: 2134352 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.9627. Min Act: -0.1700
Data Index: 3483287 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1726566 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8689. Min Act: -0.1694
Data Index: 3391789 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8689. Min Act: -0.1700
Data Index: 6009040 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8689. Min Act: -0.1700
Data Index: 7985454 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8377. Min Act: -0.1700
Data Index: 3613111 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8377. Min Act: -0.1700
Data Index: 1066539 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8377. Min Act: -0.1700
Data Index: 4438371 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 6397765 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 553543 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 1924843 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 4193820 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 5925644 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 158944 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0877. Min Range: -5.0877
Max Act: 4.8064. Min Act: -0.1700
Data Index: 2671414 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19